检索结果-内蒙古大学图书馆

International Journal of Digital Content Technology and its Applications 2011年第6期5卷 55-62页

作者： Gao, Yanyan Zhang, Honggang Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and telecommunications Beijing China

Keypoint detection is important for object recognition, image retrieval, mosaicing etc., and has attracted ample research. In this paper, we propose a novel wavelet-based detector (NWBD) based on the previous researches on keypoint detection. NWBD is performed in wavelet pyramid space, it extracts the local extrema of the energy map computed by intra-scale coefficient product (ISCP) as the candidate keypoint, and then discards some points by Hessian matrix. In the experiments, the novel detector was compared with Harris detector and SIFT detector by the evaluation of repeatability, and it achieved better performance for some scenes in the database provided by Mikolajcyzk and Schmid, such as wall, trees, and graffiti.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Feature Decoupled of Deep Mutual Information Maximization 2

Feature Decoupled of Deep Mutual Information Maximization

引用

2nd International Conference on Automation, Robotics and Computer Engineering, ICARCE 2023

作者： He, Xing Peng, Changgen Wang, Lin Tan, Weijie Wang, Zifan State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China Guizhou Big Data Academy Guizhou University Guiyang China Guizhou Minzu University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guiyang China Institute of Guizhou Aerospace Measuring and Testing Technology Guiyang China

ISBN: (纸本)9798350308341

In deep learning, supervised learning techniques usually require a large amount of expensive labeled data to train the network, and the feature representations extracted by the model usually mix multiple attributes, resulting in feature representations that are difficult to decouple and are non-interpretable, which restricts the application and development of deep learning techniques, and for this reason, it is particularly important to study decoupled feature representation methods for unsupervised learning. Although the Learning deep representations by mutual information estimation and maximization (DIM) method achieves excellent results in unsupervised learning, the feature representations learned by the DIM method still suffer from the problem of difficult decoupling. decoupling problem. To address this problem, we minimize the mutual information between the intermediate layer feature representations learned by the hidden layer of the encoder during the encoder training process, so that the features learned by each filter are as uncorrelated as possible, thus realizing feature decoupling, and our method is called FP-DIM. Finally, the effectiveness of the FP-DIM method is verified on the CIFAR-10, STL-10, and Fashion-MNIST datasets. The experiments show that our proposed FP-DIM method is more significant for the learned decouplable middle layer feature representation. Finally, we also propose a reflection of future research for the FP-DIM method, aiming to provide a research idea and direction for solving unsupervised interpretable machine learning and to lay a solid theoretical and application foundation for machine learning fields such as image classification and migration learning. © 2023 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Competing Ratio Loss for Multi-class image Classification 34

Competing Ratio Loss for Multi-class image Classification

引用

34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

作者： Zhang, Ke Wang, Xinsheng Guo, Yurong Zhao, Zhenbing Ma, Zhanyu North China Electric Power University Department of Electronic and Communication Engineering Hebei China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781728137230

Cross-entropy loss function (CEL) is widely used for training a multi-class classification deep convolutional neural network (DCNN). While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. Negative Log Likelihood Ratio Loss (NLLR) is proposed to better discriminate the correct class from competing wrong classes. But optimization of the loss function is normally presented as a minimization problem. In training DCNN, the value of NLLR is not constantly positive or negative, which affects the convergence of NLLR adversely. So, we propose competing ratio loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better widen the difference between the probability of the correct class and the probabilities of wrong classes, which also assures the value of CRL is constantly positive. Through massive experiments, we demonstrate the effectiveness and robustness of CRL on deep convolutional neural networks, our CRL outperforms CEL and NLLR on CIFAR-10/100 datasets. © 2019 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

intelligent Parking Big Data Cloud Platform Algorithm Research and Application 6

Intelligent Parking Big Data Cloud Platform Algorithm Resear...

引用

6th International Conference on Computer Information Science and Application Technology, CISAT 2023

作者： Yan, Xiaobo Zou, Xue Cai, Shan Wang, Lin Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province Guizhou Minzu University Guiyang China College of Date Science and Information Engineering Guizhou Minzu University Guiyang China

ISBN: (纸本)9781510668546

With the rapid development of the domestic economy and the increasing living standards of the people, the ownership of private cars has increased explosively. Currently, urban traffic congestion and parking difficulty have gradually become a hot topic of research from all walks of life. Parking difficulty is mainly reflected on the following aspects: first, the existing parking spaces in cities are not effectively utilized;The second reason is that drivers cannot grasp relevant information about parking spaces near the ground in real time. This article conducts in-depth research on the issue of parking difficulty. Based on the existing security monitoring systems in parking lots, real-time detection of parking spaces status is conducted based on computer vision, machine learning, and other methods. By building a comprehensive, synthesize, and multi-dimensional parking resources dynamic sensing system, a smart parking big data cloud platform is constructed to achieve the effect of intelligent indoor parking lots management. © 2023 SPIE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Tempo Variation Based Multilayer Filters for Query by Humming

Tempo Variation Based Multilayer Filters for Query by Hummin...

引用

International Conference on pattern recognition

作者： Qiang Wang Zhiyuan Guo Baoxiang Li Gang Liu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

ISBN: (纸本)9781467322164

In this paper we propose a methodology of multilayer filters based on tempo variation for realizing a query by humming (QBH) system. Firstly the original query clip is used to search for the candidate songs. If the results are unreliable, the clip is linearly scaled twice for more candidates. If the results are still unreliable, the clip is scaled more times for retrieval. To sort all the candidates, a new matching algorithm called key transposition recursive alignment (KTRA) is presented, which improves the retrieval accuracy. Experimental results on the 2010 MIREX QBH query corpus show that the proposed method can achieve a relative improvement of 20.9% as well as an acceleration factor of 2.09 simultaneously compared to a state-of-the-art method.

关键词： music query processing

来源：评论

学校读者我要写书评

暂无评论

Multi-feature content-based product image retrieval based on region of main object

Multi-feature content-based product image retrieval based on...

引用

8th International Conference on Information, Communications and Signal Processing, ICICS 2011

作者： Chai, Lunshao Zhang, Honggang Qin, Zhen Yu, Jie Qi, Yonggang Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Riverside Lab for Artificial Intelligence Research University of California Riverside Riverside CA United States

ISBN: (纸本)9781457700309

Content-based image retrieval (CBIR) has got an intense interest and seen considerable progress over the last decade. But most of the time it is only applied in laboratory. One important reason for this is the diversity of images. Different practical situations call for different taxonomy definitions of images, and lead to very different solutions. At present, and even in the foreseeable future, a general purpose CBIR system is not really possible. However, image search engines oriented at specific domains are feasible in technology and also have the actual demand. With the rapid development of electronic commerce, searching specific product by image has become one of the most attractive related research topics. In this paper, we propose a region-based method fit for the content-based retrieval of product images. The method focuses on two key issues: fast extraction of the main region, in which the product locates, as well as efficient shape and color features extraction. To show the validity of the proposed region-based method, compared experiments are carried out and illustrated on the PI 100 dataset. © 2011 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization

Dual-attention Guided Dropblock Module for Weakly Supervised...

引用

International Conference on pattern recognition

作者： Junhui Yin Siqing Zhang Dongliang Chang Zhanyu Ma Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

Attention mechanisms is frequently used to learn the discriminative features for better feature representations. In this paper, we extend the attention mechanism to the task of weakly supervised object localization (WSOL) and propose the dual-attention guided dropblock module (DGDM), which aims at learning the informative and complementary visual patterns for WSOL. This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD). To model channel interdependencies, the CAGD ranks the channel attentions and treats the top-k attentions with the largest magnitudes as the important ones. It also keeps some low-valued elements to increase their value if they become important during training. The SAGD can efficiently remove the most discriminative information by erasing the contiguous regions of feature maps rather than individual pixels. This guides the model to capture the less discriminative parts for classification. Furthermore, it can also distinguish the foreground objects from the background regions to alleviate the attention misdirection. Experimental results demonstrate that the proposed method achieves new state-of-the-art localization performance.

关键词： Location awareness Training Deep learning Adaptation models Visualization pattern recognition Automobiles

来源：评论

学校读者我要写书评

暂无评论

A bottom-up kernel of pattern learning for relation extraction

A bottom-up kernel of pattern learning for relation extracti...

引用

International Symposium on Chinese Spoken Language Processing

作者： Chunyun Zhang Weiran Xu Sheng Gao Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

Measuring the similarity of patterns is the key in pattern-based approaches in relation extraction. Most existing methods generally rely on inflexible pattern similarity measurements which often lead to low recall. In this work, a novel kernel-based model is proposed to address this problem. Depending on the pattern similarities produced by our bottom-up kernel, the most similar semantic shortest dependency patterns are selected to update seed patterns in each iteration of bootstrapping. To obtain insights of the reliability and applicability of our proposed method, we applied it to the task of English Slot Filling (ESF) in Knowledge Base Population (KBP) track at Text Analysis Conference (TAC). The experimental results validate our proposed method that importantly improves the recall which resulting in the improvement of F1 value. The effectiveness of the bottom-up kernel is also verified by further experimental results.

关键词： Kernel Semantics Computational linguistics pattern matching Natural language processing Feature extraction Computer architecture

来源：评论

学校读者我要写书评

暂无评论

WAF BASED TOPIC DETECTION IN MICRO-BLOG

WAF BASED TOPIC DETECTION IN MICRO-BLOG

引用

2012 IEEE 2nd International Conference on Cloud Computing and Intelligence systems

作者： Xiaoning Li Guang Chen Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

Micro-blog is a new information sharing tool which is more and more popular these days. In very short time there are a large number of messages posted and it is difficult for people to grasp main topics that most people are talking about. In this paper, we introduce a new text modeling method, which is called WAF, and propose a feature selection method for topic clustering based on it. In the experiments this method shows promising results, and the subsequent clustering based on it works effectively as well.

关键词： Micro-blog topic detection WAF Clustering

来源：评论

学校读者我要写书评

暂无评论

A music retrieval system based on spoken lyric queries

引用

International Journal of Advancements in Computing Technology 2012年第8期4卷 173-180页

作者： Guo, Zhiyuan Wang, Qiang Liu, Gang Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing 100876 China

This paper proposes a spoken lyric search system, which can help users to find the wanted music based on their input spoken lyric phrases. Using spoken lyric phrases to query a music retrieval system is convenient for users but challenging for developers. In our proposed system, the spoken query will be converted into text using large vocabulary continuous speech recognition (LVCSR) technique at first, and then a list of candidate lyrics and their corresponding songs will be presented by the text retrieval techniques. To guarantee the performance of the system, we propose a novel approach to improving the current technology. Specifically, a string matching method, which is based on phoneme confusion matrix, is applied to search the most similar lyrics in acoustic respect for the multiple sentence hypotheses of the input voice;and a two-level search strategy is adopted to shorten the time consuming. Experimental results show that the proposed system achieved top-1 accuracy as high as 93.98% when the search is performed within 2,000 songs, and 83.20%, a moderately satisfying accuracy, was obtained when the targeted number of songs increased to 10,000.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：